INDEX

Explanations

patterns in structured data or code, particularly related to configurations or settings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

VersionUID

-0.61

 BorderRadius

-0.57

*)

-0.52

usermodel

-0.52

hlung

-0.51

ubereitung

-0.50

—

-0.50

ieren

-0.48

---

-0.48

--

-0.47

POSITIVE LOGITS

parsedMessage

0.59

&&

0.55

implements

0.54

 esternos

0.53

||

0.52

extends

0.52

yntaxException

0.51

throws

0.48

Filmografia

0.47

 sappi

0.47

Activations Density 0.239%

patterns in structured data or code, particularly related to configurations or settings

No Comments

No Known Activations